tensor

Enable efficient SIMD programming in C++ for faster vectorized operations with a standard library interface.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

🧮 Build and optimize tensor networks in pure PyTorch, featuring Matrix Product States and Operators, with GPU support for advanced quantum computations.

⚡ Accelerate your pentesting with Blitz, a fast and efficient login page bruteforcer built in Go for unmatched speed and effectiveness.

🏗 Build REST APIs in Go easily with Barra, a stdlib-first toolkit that minimizes boilerplate and supports JWT, SQL databases, and flexible data loading.

On-device AI across mobile, embedded and edge for PyTorch

RoNet 2026: Build Transformer Models and Byte-Level BPE Tokenizers in Pure Tensors

Open Machine Learning Compiler Framework

⚡ MoX + WebGPU: a tiny, zero-dependency WebGPU compute (GPGPU) framework — typed tensors, raw WGSL kernels, and a lazy compute graph.

Compile Python source code into optimized Luau scripts for Roblox Studio using a production-grade compiler pipeline with zero dependencies.

A standalone programming language with native observer semantics, closures, dictionaries, error handling, and a self-interpreter — all in a single zero-dependency C binary

The Egison Programming Language

The AI search platform

PyTorch-equivalent deep learning framework in pure Rust — 22 crates, CUDA GPU, vision, LLMs, ONNX, autograd, distributed training

Work in Progress — Learning, Implementing & Improving

N-dimensional tensor engine with multi-dtype storage, broadcasting, and GPU acceleration (CUDA/Metal/OpenCL)

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

The V Tensor Library

Pascal N-Dimensional Arrays